Accepted for/Published in: JMIR Research Protocols
Date Submitted: Jul 7, 2020
Date Accepted: Nov 10, 2020
Developing a Bayesian Network Decision Support tool for low back pain: a pilot and protocol
ABSTRACT
Background:
Low back pain is an increasingly burdensome condition for patients and health professionals alike, and studies show that persistent pain and disability is on the increase. Previous decision support tools for management of LBP have focussed on a subset of factors due to time constraints and ease of use for the clinician. With the explosion of interest in machine learning tools and the commitment from UK government to introduce this technology in the NHS, there is an opportunity to develop a more comprehensive decision support tool. We propose to do this with a Bayesian Network, which will entail an expert elicited clinical reasoning model.
Objective:
This paper proposes a method for conducting a modified RAND Appropriateness procedure to elicit a Bayesian Network from a group of domain experts in LBP, and reports the lessons learned from the internal pilot of the procedure.
Methods:
We propose to recruit expert clinicians with a special interest in LBP from physiotherapy, general practice and sports medicine. The procedure consists of four stages. Stage 1 is an online elicitation of variables to be considered by the model, followed by a face to face workshop. Stage 2 is an online elicitation of the structure of the model, followed by a face to face workshop. Stage 3 consists of an online phase to elicit probabilities to populate the Bayesian Network. Stage 4 is a rudimentary validation of the Bayesian Network.
Results:
Ethical approval has been gained from the Research Ethics Committee at Queen Mary University of London. An internal pilot of the procedure has been run with clinical colleagues from the research team. Lessons learned have included the need for a bespoke, online elicitation tool, cognitive bias training, and development of methodology for reducing the elicitation burden on participants.
Conclusions:
The internal pilot study has yielded a clinically credible model of clinical reasoning in LBP. We believe that this method will enable us to build an AI capable Bayesian Network representative of expert clinical reasoning in low back pain.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.